US10074163B2 - Image correction method and image correction apparatus - Google Patents

Image correction method and image correction apparatus Download PDF

Info

Publication number
US10074163B2
US10074163B2 US15/334,437 US201615334437A US10074163B2 US 10074163 B2 US10074163 B2 US 10074163B2 US 201615334437 A US201615334437 A US 201615334437A US 10074163 B2 US10074163 B2 US 10074163B2
Authority
US
United States
Prior art keywords
background
pixel
brightness
image
foreground pixel
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active, expires
Application number
US15/334,437
Other languages
English (en)
Other versions
US20170116716A1 (en
Inventor
Jile JIAO
Wei Fan
Jun Sun
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
PFU Ltd
Original Assignee
Fujitsu Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujitsu Ltd filed Critical Fujitsu Ltd
Assigned to FUJITSU LIMITED reassignment FUJITSU LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: FAN, WEI, JIAO, JILE, SUN, JUN
Publication of US20170116716A1 publication Critical patent/US20170116716A1/en
Application granted granted Critical
Publication of US10074163B2 publication Critical patent/US10074163B2/en
Assigned to PFU LIMITED reassignment PFU LIMITED ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: FUJITSU LIMITED
Active legal-status Critical Current
Adjusted expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/20—Image enhancement or restoration using local operators
    • G06T5/009—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G06T5/92—Dynamic range modification of images or parts thereof based on global image properties
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30176—Document

Definitions

  • the disclosure relates to the field of image processing, and in particular to an image correction method and an image correction apparatus for correcting a non-uniform illumination image effectively.
  • FIG. 1 is a diagram of an example of a non-uniform illumination image.
  • the non-uniform illumination as shown in FIG. 1 may bring many difficulties to a subsequent image processing.
  • a background is estimated as a whole by filtering or fitting, which cannot utilize the foreground information fully, and it is difficult to reflect illumination change of the background properly.
  • an image correction method which includes: an identifying step of identifying each pixel in an image as a foreground pixel or a background pixel; a background filling step of estimating brightness of a background corresponding to a foreground pixel based on brightness and gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel, so as to obtain a background illumination map of the image according to filled backgrounds along with background pixels; and a correcting step of correcting the image based on the brightness of each pixel in the image and the background illumination map.
  • an image correction apparatus which includes: an identifying unit configured to identify each pixel in an image as a foreground pixel or a background pixel; a background filling unit configured to estimate brightness of a background corresponding to a foreground pixel based on brightness and gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel, so as to obtain a background illumination map of the image according to filled backgrounds along with background pixels; and a correcting unit configured to correct the image based on the brightness of each pixel in the image and the background illumination map.
  • FIG. 1 is a diagram showing an example of a non-uniform illumination image
  • FIG. 2 is a flowchart showing a flow example of an image correction method according to an embodiment of the present disclosure
  • FIG. 3 a shows an example of a diagram of gradient of brightness of an image
  • FIG. 3 b shows an example of a diagram of color saturation of an image
  • FIG. 3 c is a diagram showing an example of identifying an image as a foreground and a background
  • FIG. 4 is a diagram showing an example of a background filling template according to an embodiment of the present disclosure
  • FIG. 5 is a diagram showing an example of a background illumination map according to an embodiment of the present disclosure.
  • FIG. 6 is a diagram showing an example of a corrected image
  • FIG. 7 is a block diagram showing a function configuration example of an image correction apparatus according to an embodiment of the present disclosure.
  • FIG. 8 is a block diagram showing an example structure of a personal computer serving as an information processing apparatus which is capable to be adopted in an embodiment of the present disclosure.
  • FIG. 2 is a flowchart showing the flow example of the image correction method according to an embodiment of the present disclosure.
  • the image correction method may include an identifying step S 202 , a background filling step S 204 and a correcting step S 206 . Next, processing in each step is described in detail respectively.
  • each pixel in an image may be identified as a foreground pixel or a background pixel.
  • an original image may be converted into the HSV color space.
  • H channel represents a hue of a color
  • S channel represents a saturation of a color
  • V channel represents brightness of a color.
  • the foreground or the background may be identified based on information on the S channel and the V channel.
  • identifying may be performed based on a gradient of the brightness and color saturation of the pixel in the image.
  • gradient information and color saturation information may be fused to distinguish the foreground from the background.
  • a background part of the image generally has characteristics of a slow brightness change and low color saturation.
  • large gradient information may be used to describe an edge of the foreground, and high color saturation may be used to display content of the foreground.
  • FIG. 3 a shows an example of a diagram of gradient of brightness of an image.
  • FIG. 3 b shows an example of a diagram of color saturation of an image.
  • FIG. 3 a and FIG. 3 b show a diagram of gradient of brightness on the V channel based on Sobel operator and a diagram of color saturation on the S channel respectively.
  • a pixel is determined as a foreground pixel if the gradient of the brightness of the pixel in the image is greater than a first threshold or color saturation of the pixel in the image is greater than a second threshold.
  • the first threshold or the second threshold may be determined based on experience. Those skilled in the art may consider other method for determining the first threshold or the second threshold, which is not limited in the present disclosure.
  • an expansion processing may be performed on the foreground pixel.
  • FIG. 3 c is a diagram showing an example of identifying an image as a foreground and a background. Specifically, FIG. 3 c shows the diagram of identifying the image shown in FIG. 1 as a foreground and a background. White represents the foreground pixel, and black represents the background pixel.
  • the foreground and the background may be separated by using a method of inter-frame difference or based on color information or depth information, thereby identifying each pixel in the image as a foreground pixel or a background pixel.
  • brightness of a background corresponding to a foreground pixel may be estimated based on brightness and gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel, so as to obtain a background illumination map of the image according to filled backgrounds along with the background pixels.
  • background filling step S 204 to indicate background illumination better, for the image which is obtained in the identifying step S 202 and identified as the foreground pixels or the background pixels, background filling is performed on points where the foreground pixels are located, and a background illumination map is obtained according to filled backgrounds along with the background pixels.
  • the brightness of the background corresponding to the foreground pixel may be estimated by performing sub-steps of: determining background pixels with effective gradient among all the background pixels adjacent to the foreground pixel; for each one of the determined background pixels with effective gradient, calculating, based on the brightness and a gradient of the brightness of the background pixel, an estimated value of the brightness of the background corresponding to the foreground pixel; and obtaining a brightness of the background corresponding to the foreground pixel by averaging the estimated values calculated for each one of the determined background pixels, where each one of the background pixels with effective gradient may be such a pixel that in a connection direction from the foreground pixel to the pixel, pixels adjacent to the pixel are background pixels.
  • the background illumination map of the image may be obtained by an iteration process by taking the filled background as the background pixel.
  • FIG. 4 is a diagram showing an example of a background filling template according to an embodiment of the present disclosure.
  • a center of the template is a foreground pixel (for the convenience of description, this foreground pixel is abbreviated as the foreground pixel j)) with a coordinate position (i, j).
  • d 1 , d 2 , . . . d 8 are gradients of brightness of backgrounds in directions directing to the center of the template (that is the foreground pixel (i, j)) from the surroundings of the template.
  • V(x, y) may indicate a brightness of a pixel at a position (x, y) in the original image.
  • pixels adjacent to the pixel are background pixels.
  • the pixel at a position (i ⁇ 1, j ⁇ 1) and a pixel at a position (i ⁇ 2, j ⁇ 2) are both background pixels
  • the pixel at a position (i ⁇ 1, j ⁇ 1) is a background pixel with effective gradient since a pixel (i ⁇ 2, j ⁇ 2) adjacent to the pixel (i ⁇ 1, j ⁇ 1) in a connection direction from the foreground pixel (i, j) to the pixel (i ⁇ 1, j ⁇ 1) is a background pixel.
  • V(i ⁇ 1, j ⁇ 1) indicates a brightness of a background pixel at the position (i ⁇ 1, j ⁇ 1)
  • V(i ⁇ 2, j ⁇ 2) indicates a brightness of a background pixel at the position (i ⁇ 2, j ⁇ 2)
  • the pixel at the position (i ⁇ 1, j ⁇ 1) is a background pixel
  • the pixel at the position (i ⁇ 1, j ⁇ 1) is not a background pixel with effective gradient if the pixel at the position (i ⁇ 2, j ⁇ 2) is not a background pixel, and thus d 1 is non-effective.
  • the background pixels with effective gradient may be determined in sequence for 8 pixels adjacent to the foreground pixel.
  • the background pixels with effective gradient may be determined for 4 pixels adjacent to the foreground pixel in directions of up, down, left and right.
  • the background pixels with effective gradient may be determined for 4 pixels adjacent to the foreground pixel in a diagonal direction.
  • a brightness V′(i, j) of a ground corresponding to the foreground pixel (i, j) may be obtained by averaging the estimated values as calculated above.
  • a brightness V′(i, j) (that is a brightness of the ground at the position (i, j)) of a background corresponding to the foreground pixel (i, j) may be estimated according to the following formula (1):
  • background filling based on a 5 ⁇ 5 template is described as above.
  • the above description is merely an example rather than limitation.
  • a template in other size may also be used to perform background filling.
  • temples in multi-size may be used to perform background filling, such as a 5 ⁇ 5 template and a 8 ⁇ 8 template and different weighs are given to results obtained by performing background filling based on each template, and then the results are summed.
  • a brightness of background corresponding to other foreground pixel may be estimated by taking the filled background as the background pixel, and brightness of backgrounds corresponding to all the foreground pixels are estimated by an iteration process, that is, background filling is performed on points where all the foreground pixels are located.
  • a background illumination map may be obtained according to the filled backgrounds along with the background pixels.
  • FIG. 5 is a diagram showing an example of a background illumination map according to an embodiment of the present disclosure.
  • V′(x, y) may indicate a brightness at a position (x, y) in the background illumination map.
  • the image may be corrected based on the brightness of each pixel in the image and the background illumination map.
  • the image may be corrected by subtracting the brightness of each pixel in the background illumination map from the bright of each pixel in the image.
  • the image may be corrected by further taking natural illumination intensity into consideration.
  • the image correction method according to an embodiment of the present disclosure may further include a natural illumination intensity estimating step of estimating natural illumination intensity based on the brightness of all the background pixels in the image.
  • the natural illumination intensity may be estimated based on a mean value of the brightness of all the background pixels in the image. That is, a mean value of brightness of all the pixels of the background area obtained by separating the foreground and the background may be obtained, and thereby the natural illumination intensity v e is estimated.
  • the image in addition to the brightness of each pixel in the image and the background illumination map, the image may be corrected based on the natural illumination intensity.
  • the corrected image is converted from the HSV color space into the RGB color space.
  • FIG. 6 is a diagram showing an example of the corrected image. Specifically, FIG. 6 shows an image obtained by correcting the image shown in FIG. 1 . As shown in FIG. 6 , non-uniform illumination in the image shown in FIG. 1 is eliminated in the corrected image.
  • the foreground and the background are identified by fusing information on gradient of brightness of the image and information on color saturation of the image, and the background brightness is filled based on the information on the gradient of brightness and neighborhood information, thereby brightness correction can be performed on the non-uniform illumination image effectively.
  • FIG. 7 is a block diagram showing a function configuration example of an image correction apparatus 700 according to an embodiment of the present disclosure.
  • the image correction apparatus 700 may include an identifying unit 702 , a background filling unit 704 and a correcting unit 706 .
  • an identifying unit 702 may include an identifying unit 702 , a background filling unit 704 and a correcting unit 706 .
  • a correcting unit 706 may include an identifying unit 702 , a background filling unit 704 and a correcting unit 706 .
  • the identifying unit 702 may be configured to identify each pixel in an image as a foreground pixel or a background pixel.
  • the original image may be converted into the HSV color space.
  • the foreground and the background may be identified based on information on S channel and V channel.
  • the identifying may be performed based on a gradient of the brightness and color saturation of the pixel in the image.
  • a pixel in the image is determined as a foreground pixel if the gradient of the brightness of the pixel is greater than a first threshold or color saturation of the pixel is greater than a second threshold.
  • the first threshold or the second threshold may be determined based on experience. Those skilled in the art may consider other method for determining the first threshold or the second threshold, which is not limited in the present disclosure.
  • an expansion processing may be performed on the foreground pixel.
  • the foreground and the background may be separated by using a method of inter-frame difference or based on color information or depth information, thereby identifying each pixel in the image as a foreground pixel or a background pixel.
  • the background filling unit 704 may be configured to estimate brightness of a background corresponding to a foreground pixel based on brightness and gradient of the brightness of background pixels adjacent to the foreground pixel to fill the background located in a position of the foreground pixel, so as to obtain a background illumination map of the image according to filled backgrounds along with the background pixels.
  • background filling unit 704 to indicate background illumination better, for the image which is obtained in the identifying unit 702 and identified as the foreground pixel or the background pixel, background filling is performed on a point where the foreground pixel is located, and a background illumination map is obtained according to filled backgrounds along with the background pixels.
  • the brightness of the background corresponding to the foreground pixel may be estimated by: determining background pixels with effective gradient among all the background pixels adjacent to the foreground pixel; for each one of the determined background pixels with effective gradient, calculating, based on the brightness and a gradient of the brightness of the background pixel, an estimated value of the brightness of the background corresponding to the foreground pixel; and obtaining a brightness of the background corresponding to the foreground pixel by averaging the estimated values calculated for each one of the determined background pixels, where each one of the background pixels with effective gradient may be such a pixel that in a connection direction from the foreground pixel to the pixel, pixels adjacent to the pixel are background pixels.
  • the background illumination map of the image may be obtained by an iteration process by taking the filled background as the background pixel.
  • the obtained background illumination map is smoothed.
  • the correcting unit 706 may be configured to correct the image based on the brightness of each pixel in the image and the background illumination map.
  • the image may be corrected by subtracting the brightness of each pixel in the background illumination map from the bright of each pixel in the image.
  • the image may be corrected by further taking natural illumination intensity into consideration.
  • the image correction apparatus may further include a natural illumination intensity estimating unit which can be configured to estimate natural illumination intensity based on the brightness of all the background pixels in the image.
  • a natural illumination intensity estimating unit which can be configured to estimate natural illumination intensity based on the brightness of all the background pixels in the image.
  • the natural illumination intensity may be estimated based on a mean value of the brightness of all the background pixels in the image. That is, a mean value of brightness of all the pixels of the background area obtained by separating the foreground and the background may be obtained, and thereby the natural illumination intensity is estimated.
  • the image in addition to the brightness of each pixel in the image and the background illumination map, the image may be corrected based on the natural illumination intensity.
  • the corrected image is converted from the HSV color space into the RGB color space.
  • the foreground and the background are identified by fusing information on gradient of brightness of the image and information on color saturation of the image, and the background brightness is filled based on the information on the gradient of brightness and neighborhood information, thereby brightness correction can be performed on the non-uniform illumination image effectively.
  • the apparatus embodiment here corresponds to the above-described method embodiment. Therefore, as for the content not described in detail in the apparatus embodiment, reference may be made to the corresponding description in the method embodiment, which is not described here.
  • machine-executable instructions in a storage medium and a program product according to the embodiments of the present disclosure may further be configured to perform the above-described image correction method. Therefore, as for the contents not described in detail here, reference may be made to the previous corresponding description, which is not described here.
  • the storage medium used for carrying the program product including machine-readable instructions is included in the present disclosure.
  • the storage medium includes but not limited to, a floppy diskette, an optical disk, a magneto-optical disk, a memory card, a memory stick and so on.
  • the above-described series of processing and apparatuses may also be implemented by software and/or firmware.
  • program constituting the software is loaded onto the computer having a dedicated hardware structure via a storage medium or a network, such as a general purpose computer 800 shown in FIG. 8 , and the computer, when installed with various programs, can execute various functions.
  • a central processing unit (CPU) 801 performs various processing according to the program stored in a read only memory (ROM) 802 or the program loaded from the storage portion 808 to a random access memory (RAM) 803 .
  • ROM read only memory
  • RAM random access memory
  • the data required by CPU 801 to execute various processing is also stored as necessary.
  • CPU 801 , ROM 802 and RAM 803 are linked to each other via a bus 804 .
  • Input/output interface 805 is also linked to the bus 804 .
  • the following components are linked to the input/output interface 805 : an input portion 806 , including a keyboard, a mouse, etc.; an output portion 807 , including a display, such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage portion 808 including a hard disk, etc.; and a communication portion 809 , including a network interface card such as a LAN card, a modem, etc.
  • the communication portion 809 performs a communication process via a network, such as the Internet.
  • a drive 810 may also be linked to the input/output interface 805 as needed.
  • Detachable non-transitory media 811 such as disk, optical disk, magneto-optical disk, or a semiconductor memory, is mounted on the drive 810 as needed, such that a computer program read out therefrom is installed into the storage portion 808 as needed.
  • the program constituting the software is installed via the network such as the Internet or a storage medium such as the detachable media 811 .
  • such storage medium is not limited to the detachable media 811 shown in FIG. 8 in which the program is stored and distributed separately from the apparatus to provide program to the user.
  • the examples of the detachable media 811 include the disk (including a floppy disk (registered trademark)), CD (including compact disc read-only memory (CD-ROM) and a digital versatile disk (DVD)), a magneto-optical disk (including a mini disc (MD) (registered trademark)) and a semiconductor memory.
  • the storage medium may be a ROM 802 , a hard disk contained in the storage portion 808 and so on, in which the program is stored, and is distributed to a user together with the apparatus containing them.
  • multiple functions included in one unit in the above embodiments may be implemented by separate apparatus.
  • multiple functions implemented by multiple units in the above embodiments may be separately implemented by separate apparatus.
  • one of the above functions may be implemented by multiple units. Needless to say, such a configuration is included in the technical scope of the present disclosure.
  • the steps described in the flowchart include not only processing performed in the order in time series, but also include processing parallel or individually and not necessarily performed in time series. Moreover, even in the step of processing in time series, needless to say, it can be appropriately changed in that order.
  • An image correction method comprising:
  • Remark 2 The image correction method according to remark 1, wherein in the identifying step, the identifying is performed based on a gradient of the brightness and color saturation of the pixel in the image.
  • Remark 3 The image correction method according to remark 1, wherein in the background filling step, the brightness of the background corresponding to the foreground pixel is estimated by performing sub-steps of:
  • Remark 4 The image correction method according to remark 1, further comprising a natural illumination intensity estimating step of estimating natural illumination intensity based on the brightness of all the background pixels in the image.
  • Remark 5 The image correction method according to remark 4, wherein in the natural illumination intensity estimating step, the natural illumination intensity is estimated based on a mean value of the brightness of all the background pixels in the image.
  • Remark 6 The image correction method according to remark 4 or 5, wherein in the correcting step, in addition to the brightness of each pixel in the image and the background illumination map, the image is corrected based on the natural illumination intensity.
  • Remark 7 The image correction method according to remark 1, wherein in the identifying step, an expansion processing is performed on the foreground pixel.
  • Remark 8 The image correction method according to remark 1, wherein in the background filling step, the background illumination map of the image is obtained by an iteration process by taking the filled background as the background pixel.
  • Remark 9 The image correction method according to remark 1, wherein in the background filling step, the obtained background illumination map is smoothed.
  • An image correction apparatus comprising:
  • Remark 11 The image correction apparatus according to remark 10, wherein in the identifying unit, the identifying is performed based on a gradient of the brightness and color saturation of the pixel in the image.
  • Remark 12 The image correction apparatus according to remark 10, wherein in the background filling unit, the brightness of the background corresponding to the foreground pixel is estimated by:
  • the image correction apparatus according to remark 10, further comprising a natural illumination intensity estimating unit configured to estimate natural illumination intensity based on the brightness of all the background pixels in the image.
  • Remark 14 The image correction apparatus according to remark 13, wherein in the natural illumination intensity estimating unit, the natural illumination intensity is estimated based on a mean value of the brightness of all the background pixels in the image.
  • Remark 15 The image correction apparatus according to remark 13 or 14, wherein in the correcting unit, in addition to the brightness of each pixel in the image and the background illumination map, the image is corrected based on the natural illumination intensity.
  • Remark 16 The image correction apparatus according to remark 10, wherein in the identifying unit, an expansion processing is performed on the foreground pixel.
  • Remark 17 The image correction apparatus according to remark 10, wherein in the background filling unit, the background illumination map of the image is obtained by an iteration process by taking the filled background as the background pixel.
  • Remark 18 The image correction apparatus according to remark 10, wherein in the background filling unit, the obtained background illumination map is smoothed.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Facsimile Image Signal Circuits (AREA)
US15/334,437 2015-10-27 2016-10-26 Image correction method and image correction apparatus Active 2036-12-27 US10074163B2 (en)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN201510707594.4 2015-10-27
CN201510707594.4A CN106611406B (zh) 2015-10-27 2015-10-27 图像校正方法和图像校正设备
CN201510707594 2015-10-27

Publications (2)

Publication Number Publication Date
US20170116716A1 US20170116716A1 (en) 2017-04-27
US10074163B2 true US10074163B2 (en) 2018-09-11

Family

ID=58561809

Family Applications (1)

Application Number Title Priority Date Filing Date
US15/334,437 Active 2036-12-27 US10074163B2 (en) 2015-10-27 2016-10-26 Image correction method and image correction apparatus

Country Status (3)

Country Link
US (1) US10074163B2 (zh)
JP (1) JP6771134B2 (zh)
CN (1) CN106611406B (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108537740A (zh) * 2018-02-13 2018-09-14 北京航天控制仪器研究所 一种基于相邻像素统计一致性的非均匀性校正方法及系统
CN109697707B (zh) * 2018-12-29 2020-09-18 深圳美图创新科技有限公司 手绘水彩风格绘制方法及装置
CN111462001B (zh) * 2020-03-18 2023-06-09 宁波江丰生物信息技术有限公司 一种用于荧光切片扫描仪的平场校正方法
CN117422757B (zh) * 2023-10-31 2024-05-03 安徽唯嵩光电科技有限公司 一种果蔬大小分选方法、装置、计算机设备及存储介质

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6701009B1 (en) * 2000-06-06 2004-03-02 Sharp Laboratories Of America, Inc. Method of separated color foreground and background pixel improvement
US6771834B1 (en) * 1999-07-02 2004-08-03 Intel Corporation Method for segmenting a digital image
US20070036432A1 (en) * 2003-11-12 2007-02-15 Li-Qun Xu Object detection in images
US7218792B2 (en) * 2003-03-19 2007-05-15 Mitsubishi Electric Research Laboratories, Inc. Stylized imaging using variable controlled illumination
US20070263915A1 (en) * 2006-01-10 2007-11-15 Adi Mashiach System and method for segmenting structures in a series of images
US20090081775A1 (en) * 2005-05-25 2009-03-26 Stiftesen Unversitetsforskning Bergen Microscope system and screening method for drugs, physical therapies and biohazards
US20090323089A1 (en) * 2008-06-24 2009-12-31 Makoto Hayasaki Image processing apparatus, image forming apparatus, image processing method, and computer-readable storage medium storing image processing program
US20110261264A1 (en) * 2008-12-24 2011-10-27 Baham Zafarifar Image Processing
US8155442B2 (en) * 2008-02-04 2012-04-10 The Neat Company, Inc. Method and apparatus for modifying the histogram of an image
US20120242789A1 (en) * 2011-03-25 2012-09-27 Chung Hua University Apparatus for generating real-time stereoscopic image and method thereof
US20130106848A1 (en) * 2011-05-12 2013-05-02 Khang Nguyen Image generation apparatus and image generation method
US20130301918A1 (en) * 2012-05-08 2013-11-14 Videostir Ltd. System, platform, application and method for automated video foreground and/or background replacement
US8907972B2 (en) * 2011-07-19 2014-12-09 Fujitsu Limited Image processing device and method
US20150146020A1 (en) * 2013-11-28 2015-05-28 Sharp Kabushiki Kaisha Determining apparatus, mobile terminal apparatus, and recording medium
US9204011B1 (en) * 2014-07-07 2015-12-01 Fujitsu Limited Apparatus and method for extracting a background luminance map of an image, de-shading apparatus and method
US9256782B2 (en) * 2014-02-14 2016-02-09 Fujitsu Limited Apparatus and method for processing document image to estimate luminance image from luminance component image adjusted according to estimated or largest luminance values and predetermined criterion
US9294655B2 (en) * 2013-12-06 2016-03-22 Fujitsu Limited Apparatus for and method of processing document image
US9418307B2 (en) * 2014-01-20 2016-08-16 Fujitsu Limited Method and apparatus for smoothing image
US9519975B2 (en) * 2014-01-08 2016-12-13 Hong Kong Applied Science And Technology Research Institute Co. Ltd. Method of detecting edge under non-uniform lighting background

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6771834B1 (en) * 1999-07-02 2004-08-03 Intel Corporation Method for segmenting a digital image
US6701009B1 (en) * 2000-06-06 2004-03-02 Sharp Laboratories Of America, Inc. Method of separated color foreground and background pixel improvement
US7218792B2 (en) * 2003-03-19 2007-05-15 Mitsubishi Electric Research Laboratories, Inc. Stylized imaging using variable controlled illumination
US20070036432A1 (en) * 2003-11-12 2007-02-15 Li-Qun Xu Object detection in images
US20090081775A1 (en) * 2005-05-25 2009-03-26 Stiftesen Unversitetsforskning Bergen Microscope system and screening method for drugs, physical therapies and biohazards
US20070263915A1 (en) * 2006-01-10 2007-11-15 Adi Mashiach System and method for segmenting structures in a series of images
US8155442B2 (en) * 2008-02-04 2012-04-10 The Neat Company, Inc. Method and apparatus for modifying the histogram of an image
US20090323089A1 (en) * 2008-06-24 2009-12-31 Makoto Hayasaki Image processing apparatus, image forming apparatus, image processing method, and computer-readable storage medium storing image processing program
US20110261264A1 (en) * 2008-12-24 2011-10-27 Baham Zafarifar Image Processing
US20120242789A1 (en) * 2011-03-25 2012-09-27 Chung Hua University Apparatus for generating real-time stereoscopic image and method thereof
US20130106848A1 (en) * 2011-05-12 2013-05-02 Khang Nguyen Image generation apparatus and image generation method
US8907972B2 (en) * 2011-07-19 2014-12-09 Fujitsu Limited Image processing device and method
US20130301918A1 (en) * 2012-05-08 2013-11-14 Videostir Ltd. System, platform, application and method for automated video foreground and/or background replacement
US20150146020A1 (en) * 2013-11-28 2015-05-28 Sharp Kabushiki Kaisha Determining apparatus, mobile terminal apparatus, and recording medium
US9294655B2 (en) * 2013-12-06 2016-03-22 Fujitsu Limited Apparatus for and method of processing document image
US9519975B2 (en) * 2014-01-08 2016-12-13 Hong Kong Applied Science And Technology Research Institute Co. Ltd. Method of detecting edge under non-uniform lighting background
US9418307B2 (en) * 2014-01-20 2016-08-16 Fujitsu Limited Method and apparatus for smoothing image
US9256782B2 (en) * 2014-02-14 2016-02-09 Fujitsu Limited Apparatus and method for processing document image to estimate luminance image from luminance component image adjusted according to estimated or largest luminance values and predetermined criterion
US9204011B1 (en) * 2014-07-07 2015-12-01 Fujitsu Limited Apparatus and method for extracting a background luminance map of an image, de-shading apparatus and method

Also Published As

Publication number Publication date
CN106611406B (zh) 2019-08-16
JP6771134B2 (ja) 2020-10-21
CN106611406A (zh) 2017-05-03
JP2017085570A (ja) 2017-05-18
US20170116716A1 (en) 2017-04-27

Similar Documents

Publication Publication Date Title
US10187546B2 (en) Method and device for correcting document image captured by image pick-up device
US10074163B2 (en) Image correction method and image correction apparatus
US10204432B2 (en) Methods and systems for color processing of digital images
US7689036B2 (en) Correction of blotches in component images
US6707940B1 (en) Method and apparatus for image segmentation
US10477128B2 (en) Neighborhood haze density estimation for single-image dehaze
EP3139343B1 (en) Image processing apparatus, image processing method, and a program
KR102084343B1 (ko) 배경 제거
US9727984B2 (en) Electronic device and method for processing an image
US9704227B2 (en) Method and apparatus for image enhancement
EP2977954B1 (en) Image processing device, imaging device, monitoring system, encoding device, image processing method
US8655100B2 (en) Correcting an artifact in an image
US7620241B2 (en) Artifact reduction in a digital video
US20220053107A1 (en) Image processing method, image forming apparatus, and storage medium
KR20180127913A (ko) 화상 처리 장치, 화상 처리 방법, 및 프로그램
US20120144304A1 (en) System and method for reducing artifacts in images
EP1231567A2 (en) Image artifact removal technique for liquid crystal projectors
EP1483899B1 (en) Reducing halos in spatially dependent gamut mapping
EP3038057A1 (en) Methods and systems for color processing of digital images
JPH10232915A (ja) 画像処理装置およびその方法
US8554005B1 (en) Digital image enhancement method and system that embolden or thin image features
WO2016102386A1 (en) Methods and systems for color processing of digital images
CN104346599A (zh) 一种色彩边缘的检测方法及图像处理设备
US20240249398A1 (en) Image processing apparatus, image processing method, and non-transitory computer-readable storage medium
JP5862370B2 (ja) 画像処理装置、画像処理方法及びプログラム

Legal Events

Date Code Title Description
AS Assignment

Owner name: FUJITSU LIMITED, JAPAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:JIAO, JILE;FAN, WEI;SUN, JUN;REEL/FRAME:040192/0856

Effective date: 20161018

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: PFU LIMITED, JAPAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:FUJITSU LIMITED;REEL/FRAME:053680/0172

Effective date: 20200615

MAFP Maintenance fee payment

Free format text: PAYMENT OF MAINTENANCE FEE, 4TH YEAR, LARGE ENTITY (ORIGINAL EVENT CODE: M1551); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY

Year of fee payment: 4